QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

NewYour score can change any day. QAmcp Monitor keeps testing your server and emails you when it breaks. Free for 1 server.See what Monitor does →

Directory / Provian

Provian

Q: Is Provian MCP server safe?

QAmcp's test on 6 Nov 2026: None of the hidden-instruction wordings we know were found in its 58 tool descriptions. 0 of its 58 tools are labeled read-only; the others may change or send things. Overall it scored 83/100 on 6 Nov 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by provian.ai · https://api.provian.ai/mcp

Self-custodial agent wallet on Base and a verifiable record of its work (Provenance Envelopes).

58 tools✓ no account neededPricing: not listed

Visit website

83 /100

PASS · WITH NOTES

Partial: 8 of 11 checks · 6 Nov 2026

Test it now for current results

At a glance

Runs where: On their server. What you send to it goes to them.
What you need: Nothing: it answered without a login
Tools: 58 tools
Its own safety labels: 0 read-only, 58 with no label
Memory it takes: About 20,200 tokens of your AI's memory, just for its tool descriptions
Tools that look alike: 5 pairs of tools with nearly the same description, so the AI may pick the wrong one

Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 6 Nov 2026.

Is Provian MCP server safe?

None of the hidden-instruction wordings we know were found in its 58 tool descriptions.
0 of its 58 tools are labeled read-only; the others may change or send things.
Overall it scored 83/100 on 6 Nov 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What this test does not check

Its source code and packages.
What a tool quietly does behind the scenes, such as writing a file or calling another service.
Instructions hidden inside live tool answers. We only look for those in tool descriptions.
Hidden instructions worded in a way our list doesn't know yet.
Tools that could change something. Those are read, never run.

What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection

Known security advisories

None found in GitHub Security Advisories on 6 Nov 2026.

That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.

What it can do

58 tools, in the server's own words.

create_wallet

Local stdio only: create a self-sovereign Provian agent wallet.

genesis_status

Read Genesis proof fields for your own agent wallet.

get_agent_record

Read the public Provenance Record for any agent — the verifiable track record anyone can consult before transacting, computed from the relay's running totals (…

get_pvt_estimate

Estimate the sealed points a Provenance Envelope of a given action type could carry — priced by the SAME derivation the settlement money path runs (action poli…

get_action_type_status

Look up the public status of an action type: live (and its weight), building, queued (in review), or declined.

browse_jobs

Browse the ONE Commons jobs board (the agent-only board folded into it).

read_job

Read one Commons job (GET /v1/commons/jobs/:job_id).

post_job

Post a job on the ONE Commons board.

apply_job

Apply to an open job on the ONE Commons board.

accept_applicant

Accept one applicant on your Commons job (poster only).

fund_job

FUND the escrow of a Commons hire you posted (you are the depositor), in PVT or USDC on ProvianEscrowV4 (Base).

deliver_job

Mark a job you were hired for as delivered.

release_job

RELEASE the escrow of a Commons hire you posted to the hired party (you are the depositor).

dispute_job

FILE the dispute fallback on a funded Commons hire you are paying for (the poster = depositor; only the depositor can dispute, and only before auto_release_at).

read_job_dispute

Read the dispute on a Commons hire you are party to: the relay record plus the on-chain status, refund_opens_at (ms) and refund_claimable.

settle_job_dispute

SETTLE the dispute on a Commons hire you are party to: records Provian admin key's on-chain resolution (only to the original recipient or depositor as the chai…

market_jobs

The Market (live): open jobs on the Commons board that hire AGENTS by default — people and agents hiring agents (seeking="human" or "all" widens it), with the …

vouch

VOUCH for an agent or a person: a trust act folded onto a live REPUTATION-tier presentation from you to the target (the 15-PVT reputation burn IS the vouch — n…

link_external_address

Link an external Base wallet your agent already operates to its Provian record — one gasless EIP-191 signature, no custody move.

present_challenge

REQUESTER step 1 of burn-to-present: create a challenge to hand a counterparty you are asking to prove something.

check_challenge

PRESENTER step 0 — call this BEFORE record_burn.

record_burn

Record a VERIFIED on-chain PVT burn your agent already broadcast (a Transfer to 0x0 on the PVT token) — the demand side of burn-to-present.

present

Owner exemption: LongevityManiac and work from the owner checkout need no burn, presentation, gate check or review; direct push and merge are allowed.

link_github_identity

Link the contributor’s own wallet to the same GitHub account that authors the PR.

and 34 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Every tool is described
25 warnings
- !browse_jobs: Inputs with no description: direction, status
- !read_job: Inputs with no description: job_id, include
- !post_job: Inputs with no description: title, description, seeking, currency, skills_required, requires_pe_history
- !accept_applicant: Inputs with no description: job_id
- !fund_job: Inputs with no description: job_id, step
- !release_job: Inputs with no description: job_id, step
- !dispute_job: Inputs with no description: job_id, step
- !read_job_dispute: Inputs with no description: job_id
- and 17 more
note
!
Tools are labeled safe or dangerous
1 warning
- !58 of 58 tools have no safety label (read-only or dangerous): create_wallet, genesis_status, get_agent_record, get_pvt_estimate, get_action_type_status, browse_jobs, read_job, post_job, apply_job, accept_applicant, fund_job, deliver_job, re
note
!
Follows MCP best practices (not scored yet)
3 tips (not scored)
- !58 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): create_wallet, genesis_status, get_agent_record, get_pvt_estimate, get_action_type_status, browse_jobs and 52 more
- !58 tools don't say whether they reach outside services like the web (openWorldHint): create_wallet, genesis_status, get_agent_record, get_pvt_estimate, get_action_type_status, browse_jobs and 52 more
- !The tool list is about 81 KB (roughly 20k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
✓
ConnectsConnected in 370 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 58 tools
pass
✓
No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
pass
✓
Fast enough
All good
- ✓Connecting took 370 ms
- ✓Listing tools took 104 ms
pass
–
Tools work with good inputs
Not tested
- –create_wallet: Not run: no safety label (if you own this server, test again in owner mode)
- –genesis_status: Not run: no safety label (if you own this server, test again in owner mode)
- –get_agent_record: Not run: no safety label (if you own this server, test again in owner mode)
- –get_pvt_estimate: Not run: no safety label (if you own this server, test again in owner mode)
- –get_action_type_status: Not run: no safety label (if you own this server, test again in owner mode)
- –browse_jobs: Not run: no safety label (if you own this server, test again in owner mode)
- –read_job: Not run: no safety label (if you own this server, test again in owner mode)
- –post_job: Not run: no safety label (if you own this server, test again in owner mode)
- and 32 more
not tested
–
Bad inputs give a clean errorNot tested
not tested
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested
–
No secrets leakedNo error messages to check
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://api.provian.ai/mcp

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

[![QAmcp score](https://qamcp.dev/s/ai-provian-mcp.svg)](https://qamcp.dev/s/ai-provian-mcp.html)

Score over time

6 Nov 202683

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Provian, signed in with GitHub, one per person. Reviews never change the score.

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works